savy91

dropped you a message

sms / WhatsApp

fine that was possible with Twilio even before

iMessage

How did you go about this?

FYI frosting does not work in Safari

Send me a message if you are interested in the domain https://human-use.com

I started working on something similar to your project months ago then never released anything.

It would be cool to have it on Coolify

Have you validated that people are going to pay that amount of money without any proof they are actually good ideas, with no refund option and no information on what you mean by “validated”?

I fail to see how Acclara is relevant by looking at their homepage. The link you sent is behind a sign up page.

Is there any way to sign up and try this without going through the sales call/demo?

I have been using them for a little more than a year to add email capability to bots: https://www.cloudmailin.com/

What would be the advantage of switching over?

Too long/too much movement in my opinion

I would suggest you add some screenshots and a better explanation about the actual app usage on the landing page, I had to go to the Play Store to see some screenshots before downloading the app.

I still have my NZ90. The hardware was amazing, the software not so much

Is it just a mock up and a landing page or is the MVP actually functional?

Am I wrong thinking this could very well be the backbone of an alternative to the Rabbit AI? Where you basically end up having possibly infinite tools for your LLM assistant to use to reach a goal without having to build api integrations.

Function call is there only for api access, unless you create a ChatGPT plugin.

Also, the api allows the developer to force gpt to call a specific function.

Amazing! I am working on projexts where we use LLMs and Typescript and and besides langchain-js which can be only described as bloatware, I can never find anything and find myself reinvent the wheel most of the time.

I worked on something like this for a client and got pretty good results with this model: https://civitai.com/models/6431?modelVersionId=23104

I spent a while looking for decent loras but eventually settled on this because there are just too many porn fine tunes on civitai and it would take a lifetime to test them all.

The product I built allows users to ask pretty much anything (it's a sort of sex chatbot that also sends photos) and the problem is when people start asking super weird stuff and you end up with girls with 4 feet.

Or maybe they like that and it's not a problem at all, who knows.

Worst part of langchain is the "documentation". Especially the one about the javascript implementation

I was going with "oh yes? Show me what you sell" then I clicked on your username. You are doing an amazing job!

Have you tried this? https://apify.com/vdrmota/contact-info-scraper it can work with 50 input urls at a time.

I could say the same for gpt3.5. Through the API I am getting many more "sorry but as a language model" with the prompts I have been using for a while

Somehow it feels different this time, the other technologies you mentioned were more niche and you could avoid talking about them. GPT is more pervasive. My Instagram feed was not full of microservices influencers at the time...

I realized only now that with this post I contributed to the GPT-chatter, sorry world!

Is it so much better? I honestly don't see that much of a difference with "good prompts" between GPT4 and GPT3.5 in chatgpt.

OP is referring to GPT4 API

How do you plan to keep this running for free?

Pretty cool. Do you plan on monetizing this somehow exposing an API or would you mind sharing the approach you took?

Curiously the example you mention is exactly what you get by using Linux with KDE and an Android phone using KDE Connect.

What are the differences compared to posthog?

Option B would be the most realistic and the one that makes most sense to me